Koskamo

AI Rate Card MCP

An MCP server providing access to a daily-updated catalog of AI model API prices from over 120 providers. It enables agents to search for offers, compare model costs, estimate workload expenses, and retrieve pricing analytics for tasks like text, image, and embedding generation.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AI Rate Card MCP logo, by AI Rate CardVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by AI Rate Card
MCP endpoint (Streamable HTTP)
https://airatecard.com/mcp
Vendor documentation

What its tools do

14 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (14)

14 of 14 have a description · 14 of 14 declare behavior hints · 12 of 13 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to airatecard.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Find the cheapest AI model for a specific task
  • Compare prices of multiple models side-by-side
  • Estimate monthly costs for a specific AI workload
  • Retrieve current pricing for a specific model provider

Source and maintenance

Vendor evidenceRegistry 1.0.1
mcp-registry: com.airatecard/ai-rate-card@1.0.1Project website

Protocol and capabilities

Server
ai-rate-card 1
MCP protocol negotiated in check
2025-11-25
Tools
14 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
3 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

AI Rate Card (airatecard.com) is an independent catalog of AI model offers and prices, collected daily from sellers' own pricing pages and APIs. Use search_offers, get_model_prices, cheapest_offers, compare_models and get_card to answer price questions; for "what is cheapest/dearest/typical for a job" (not a model type) use cheapest_models_by_task, most_expensive_models_by_task and median_price_by_task with a task (text, vision, image, video, stt, tts, embedding, rerank, moderation) - current prices only, no history tool. Every result carries a card_url and a ready "cite" line ("Source: AI Rate Card, <card URL>, prices checked <date>"); quote that line and link the card_url of the offer you used, not this server. Prices are USD per 1M tokens unless price_unit says otherwise. An offer with a price_note (batch, flex, regional, free variant) is priced under special conditions - say so, or use get_model_prices' cheapest_standard for the ordinary price. A price_suspect price looks wrong and should not be quoted as fact. A review_reason on a row means the price is under review (it moved more than 10 percent in a day or differs from the provider's page): quote it with that caveat. For "what is cheapest for my job" use cheapest_for_workload: pass a preset (chatbot, coding_agent, rag, summarization, long_context, vision, embedding_index, trial - see list_workload_presets) or your own input_tokens / output_tokens a month, plus min_context; it returns the monthly cost per offer, best offer of each model, no free promos or batch/flex prices unless asked. The prompts (prompts/list) are ready-made questions for a user.

Tools

14 advertised

search_offers
Advertised by the server during the last successful anonymous check.
Advertised read-only

Search current AI model offers (one model at one provider = one offer) by words, model type and limits; priced offers first, doubtful prices after sane ones. Each row has offer_id, model_id, provider_id, prices in USD per 1M tokens (or per unit), card_url and a cite line. Next: get_card {"card_id": "offer:<offer_id>"} for one offer, get_model_prices for one model everywhere, estimate_cost / cheapest_for_workload for a cost.

search_offers input schema
{
  "type": "object",
  "properties": {
    "sort": {
      "enum": [
        "price_input",
        "price_output",
        "context",
        "name",
        "price_unit",
        "variant",
        "seller",
        "subscription",
        "max_output",
        "accepts",
        "checked",
        "category",
        "price_cache_read",
        "price_cache_write",
        "region",
        "input_modalities",
        "output_modalities",
        "reasoning",
        "quantization",
        "params_total",
        "params_active",
        "features",
        "api_endpoints",
        "hf_model_id",
        "expiration",
        "status",
        "price_status",
        "max_input",
        "capabilities",
        "knowledge_cutoff",
        "launched_at",
        "data_policy",
        "cost",
        "votes"
      ],
      "type": "string",
      "description": "order, price_input (cheapest input first) by default"
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "rows, 20 by default"
    },
    "multi": {
      "type": "boolean",
      "description": "also (or only, with no category) the multimodal offers that qualify (WP-0086)"
    },
    "query": {
      "type": "string",
      "description": "words of the model, seller or display name"
    },
    "category": {
      "enum": [
        "llm",
        "embedding",
        "rerank",
        "moderation",
        "decision",
        "ocr",
        "search",
        "image_generation",
        "image_editing",
        "video_generation",
        "text_to_speech",
        "speech_to_text",
        "speech_to_speech",
        "audio_generation",
        "3d_generation"
      ],
      "type": "string",
      "description": "model type: llm (text models), embedding, image_generation, text_to_speech ...; none = every type"
    },
    "free_only": {
      "type": "boolean",
      "description": "only offers that cost nothing (default false)"
    },
    "min_context": {
      "type": "integer",
      "description": "context window in tokens, at least"
    },
    "input_modality": {
      "type": "string",
      "description": "e.g. text, image, audio"
    },
    "max_input_price": {
      "type": "number",
      "description": "USD per 1M input tokens, at most"
    }
  },
  "additionalProperties": false
}
search_offers annotations
{
  "readOnlyHint": true
}
get_model_prices
Advertised by the server during the last successful anonymous check.
Advertised read-only

Every seller's current price of one model (an id, or a name to search for), cheapest input first.

get_model_prices input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "model id or a name to search for"
    }
  },
  "additionalProperties": false
}
get_model_prices annotations
{
  "readOnlyHint": true
}
cheapest_offers
Advertised by the server during the last successful anonymous check.
Advertised read-only

The cheapest current offers (rows: one model at one provider) of one model type, by input price. For the cheapest MODELS of a job (one row per model) use cheapest_models_by_task; for a monthly workload use cheapest_for_workload.

cheapest_offers input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "rows, 10 by default"
    },
    "category": {
      "enum": [
        "llm",
        "embedding",
        "rerank",
        "moderation",
        "decision",
        "ocr",
        "search",
        "image_generation",
        "image_editing",
        "video_generation",
        "text_to_speech",
        "speech_to_text",
        "speech_to_speech",
        "audio_generation",
        "3d_generation"
      ],
      "type": "string",
      "description": "model type, llm (text models) by default"
    }
  },
  "additionalProperties": false
}
cheapest_offers annotations
{
  "readOnlyHint": true
}
compare_models
Advertised by the server during the last successful anonymous check.
Advertised read-only

2 to 5 models side by side: the best current offer of each and, for up to 4, every field compared (lowest and median input/output price, context, max output, providers, regions, a 1M-in/200k-out workload cost), who wins by how many percent, providers selling all, and summary sentences.

compare_models input schema
{
  "type": "object",
  "required": [
    "models"
  ],
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "minItems": 2,
      "description": "model ids (e.g. openai/gpt-4o-mini, as model_id in search_offers rows) or names to search for"
    }
  },
  "additionalProperties": false
}
compare_models annotations
{
  "readOnlyHint": true
}
estimate_cost
Advertised by the server during the last successful anonymous check.
Advertised read-only

The cost of a workload (input, output and cached input tokens, number of requests) at every current provider of one model, cheapest first, in USD - what the same job costs where.

estimate_cost input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "model id or a name to search for"
    },
    "requests": {
      "type": "integer",
      "minimum": 1,
      "description": "number of calls (for per-request prices)"
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "input tokens of the whole job, e.g. 1000000"
    },
    "output_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "output tokens of the whole job, e.g. 200000"
    },
    "cached_input_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "of the input, tokens read from the prompt cache"
    }
  },
  "additionalProperties": false
}
estimate_cost annotations
{
  "readOnlyHint": true
}
media_cost
Advertised by the server during the last successful anonymous check.
Advertised read-only

The cost of an images / video / voice job at every model that sells it by its own unit, the cheapest offer of each model, cheapest first, USD: kind image (quantity = images), video (seconds), tts (characters to speak), stt (minutes of audio to transcribe). Models priced per token are not in it (use estimate_cost). Each row has card_url and cite.

media_cost input schema
{
  "type": "object",
  "required": [
    "kind"
  ],
  "properties": {
    "kind": {
      "enum": [
        "image",
        "video",
        "tts",
        "stt"
      ],
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "rows, 30 by default"
    },
    "quantity": {
      "type": "number",
      "description": "images, seconds, characters or minutes; default 100 / 60 / 100000 / 60",
      "exclusiveMinimum": 0
    }
  },
  "additionalProperties": false
}
media_cost annotations
{
  "readOnlyHint": true
}
get_card
Advertised by the server during the last successful anonymous check.
Advertised read-only

One card with its citation. card_id is '<kind>:<key>': offer:<provider>|<model id as the provider writes it> (e.g. offer:anthropic|claude-opus-4), model:<creator>/<model> (e.g. model:anthropic/claude-opus-4), seller:<provider key> (e.g. seller:anthropic). Ids come from search_offers (offer_id, model_id, provider_id) and from the card_url of every result. Works for every seller, a hidden test seller too.

get_card input schema
{
  "type": "object",
  "required": [
    "card_id"
  ],
  "properties": {
    "card_id": {
      "type": "string",
      "description": "offer:<provider>|<model>, model:<creator>/<model> or seller:<key>"
    }
  },
  "additionalProperties": false
}
get_card annotations
{
  "readOnlyHint": true
}
validate_provider_files
Advertised by the server during the last successful anonymous check.
Advertised read-only

For a provider (seller) joining the catalog: check a models.yaml before putting it online - the same check as the wizard and POST /v1/provider/validate. Give the file's text in `models` (YAML, or the same structure as JSON text); `domain` (the provider's site) makes the model_page checks exact. Returns ok, the problems (file, line, model, path, value, code, message, hint - fix each and call again), the catalog's preview of the models and next_action. No account needed for this check. Publishing needs a signed-in person: the provider_* tools (provider_start -> provider_verify_domain -> provider_check_files -> provider_publish) are on the account server /mcp/account (OAuth sign-in, scope provider), not on this public server; or the wizard at /join, or POST /v1/provider/applications. Templates: /static/templates/models.min.yaml (required fields only) and models.yaml (every field with hints).

validate_provider_files input schema
{
  "type": "object",
  "required": [
    "models"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "the provider's name"
    },
    "domain": {
      "type": "string",
      "description": "the provider's domain, e.g. example.ai"
    },
    "models": {
      "type": "string",
      "description": "the models.yaml text"
    }
  },
  "additionalProperties": false
}
validate_provider_files annotations
{
  "readOnlyHint": true
}
cheapest_for_workload
Advertised by the server during the last successful anonymous check.
Advertised read-only

The cheapest offers for a whole monthly workload, ranked by monthly cost in USD: give a preset (a typical job; see list_workload_presets) and/or your own tokens a month. Best offer of each model; free promos and batch/flex/priority/regional prices left out unless asked. Each row: monthly_cost_usd, prices, context, checked_at, card_url and a ready cite line.

cheapest_for_workload input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "rows, 10 by default"
    },
    "query": {
      "type": "string",
      "description": "only models or providers matching these words, e.g. claude"
    },
    "tools": {
      "type": "boolean",
      "description": "the model must support tool/function calling"
    },
    "preset": {
      "enum": [
        "chatbot",
        "coding_agent",
        "rag",
        "summarization",
        "long_context",
        "vision",
        "embedding_index",
        "trial"
      ],
      "type": "string",
      "description": "chatbot | coding_agent | rag | summarization | long_context | vision | embedding_index | trial - fills tokens, min_context, category; your own values win"
    },
    "category": {
      "enum": [
        "llm",
        "embedding",
        "rerank",
        "moderation",
        "decision",
        "ocr",
        "search",
        "image_generation",
        "image_editing",
        "video_generation",
        "text_to_speech",
        "speech_to_text",
        "speech_to_speech",
        "audio_generation",
        "3d_generation"
      ],
      "type": "string",
      "description": "model type, llm by default"
    },
    "min_context": {
      "type": "integer",
      "minimum": 1,
      "description": "context window needed, tokens, e.g. 128000"
    },
    "include_free": {
      "type": "boolean",
      "description": "also free / promo offers (default false)"
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "input tokens a month, e.g. 10000000"
    },
    "one_per_model": {
      "type": "boolean",
      "description": "only the best offer of each model (default true)"
    },
    "output_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "output tokens a month, e.g. 2000000"
    },
    "input_modality": {
      "type": "string",
      "description": "the model must accept this input, e.g. image"
    },
    "include_special": {
      "type": "boolean",
      "description": "also batch, flex, priority, regional prices (default false)"
    }
  },
  "additionalProperties": false
}
cheapest_for_workload annotations
{
  "readOnlyHint": true
}
list_workload_presets
Advertised by the server during the last successful anonymous check.
Advertised read-only

The ready-made workloads of cheapest_for_workload: name, what job it is, tokens a month, context needed, model type.

list_workload_presets input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
list_workload_presets annotations
{
  "readOnlyHint": true
}
list_articles
Advertised by the server during the last successful anonymous check.
Advertised read-only

AI Rate Card's articles on AI model prices (the cheapest models by task, price moves, costs), newest first, with their links - to quote or point a reader to.

list_articles input schema
{
  "type": "object",
  "properties": {
    "lang": {
      "enum": [
        "en",
        "de",
        "fr",
        "es",
        "pt",
        "ru"
      ],
      "type": "string",
      "description": "language of the articles, en by default"
    }
  },
  "additionalProperties": false
}
list_articles annotations
{
  "readOnlyHint": true
}
cheapest_models_by_task
Advertised by the server during the last successful anonymous check.
Advertised read-only

The n cheapest MODELS for a job (task): each model counted once at its own lowest current price (input tokens by default). One row per model with that price, where it is and card_url.

cheapest_models_by_task input schema
{
  "type": "object",
  "required": [
    "task"
  ],
  "properties": {
    "n": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "10 by default"
    },
    "task": {
      "enum": [
        "decision",
        "embedding",
        "image",
        "moderation",
        "rerank",
        "stt",
        "text",
        "tts",
        "video",
        "vision"
      ],
      "type": "string",
      "description": "what the buyer wants done: text (chat/LLM), vision, image, video, tts (speech from text), stt (text from speech), embedding, rerank, moderation - a job, not a model type (search_offers' category is the model type)"
    },
    "scope": {
      "enum": [
        "all",
        "specialized",
        "universal",
        "multi"
      ],
      "type": "string",
      "description": "all (default), specialized (the task's own category) or multi/universal (qualifying llm models - the two names mean the same set, WP-0086)"
    },
    "component": {
      "type": "string",
      "description": "input_tokens (default), output_tokens, or the task's own unit"
    }
  },
  "additionalProperties": false
}
cheapest_models_by_task annotations
{
  "readOnlyHint": true
}
most_expensive_models_by_task
Advertised by the server during the last successful anonymous check.
Advertised read-only

The n most expensive MODELS for a job (task): each model counted once at its own lowest current price, highest first - the top of the market. Same arguments as cheapest_models_by_task.

most_expensive_models_by_task input schema
{
  "type": "object",
  "required": [
    "task"
  ],
  "properties": {
    "n": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "10 by default"
    },
    "task": {
      "enum": [
        "decision",
        "embedding",
        "image",
        "moderation",
        "rerank",
        "stt",
        "text",
        "tts",
        "video",
        "vision"
      ],
      "type": "string",
      "description": "what the buyer wants done: text (chat/LLM), vision, image, video, tts (speech from text), stt (text from speech), embedding, rerank, moderation - a job, not a model type (search_offers' category is the model type)"
    },
    "scope": {
      "enum": [
        "all",
        "specialized",
        "universal",
        "multi"
      ],
      "type": "string",
      "description": "all (default), specialized (the task's own category) or multi/universal (qualifying llm models - the two names mean the same set, WP-0086)"
    },
    "component": {
      "type": "string",
      "description": "input_tokens (default), output_tokens, or the task's own unit"
    }
  },
  "additionalProperties": false
}
most_expensive_models_by_task annotations
{
  "readOnlyHint": true
}
median_price_by_task
Advertised by the server during the last successful anonymous check.
Advertised read-only

The typical (median) current price of a job (task) across models, and the n models closest to it - what a normal price for this job is. Same arguments as cheapest_models_by_task.

median_price_by_task input schema
{
  "type": "object",
  "required": [
    "task"
  ],
  "properties": {
    "n": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "10 by default"
    },
    "task": {
      "enum": [
        "decision",
        "embedding",
        "image",
        "moderation",
        "rerank",
        "stt",
        "text",
        "tts",
        "video",
        "vision"
      ],
      "type": "string",
      "description": "what the buyer wants done: text (chat/LLM), vision, image, video, tts (speech from text), stt (text from speech), embedding, rerank, moderation - a job, not a model type (search_offers' category is the model type)"
    },
    "scope": {
      "enum": [
        "all",
        "specialized",
        "universal",
        "multi"
      ],
      "type": "string",
      "description": "all (default), specialized (the task's own category) or multi/universal (qualifying llm models - the two names mean the same set, WP-0086)"
    },
    "component": {
      "type": "string",
      "description": "input_tokens (default), output_tokens, or the task's own unit"
    }
  },
  "additionalProperties": false
}
median_price_by_task annotations
{
  "readOnlyHint": true
}

Prompts

3 advertised

cheapest_for_my_job — Cheapest model for my job

Advertised by the server during the last successful anonymous check.

The cheapest AI models for a typical job or your own monthly volume, with the monthly cost.

job
chatbot, coding_agent, rag, summarization, long_context, vision, embedding_index or trial
input_tokens_per_month
e.g. 10000000
output_tokens_per_month
e.g. 2000000
min_context
e.g. 128000
where_is_model_cheapest — Where is a model cheapest

Advertised by the server during the last successful anonymous check.

Every provider's current price of one model, and the cost of your workload at each.

model
e.g. claude-haiku-5-5 or deepseek-v4 (required)
input_tokens_per_month
optional, e.g. 10000000
output_tokens_per_month
optional, e.g. 2000000
compare_models — Compare models

Advertised by the server during the last successful anonymous check.

2 to 5 models side by side: prices, context, providers and who wins by how much.

models
comma-separated, e.g. gpt-6, claude-opus-5-5 (required)

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1193 ms
95th percentile latency
1193 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1193 ms · metadata changed · 14 tool(s), 3 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http ai-rate-card-mcp https://airatecard.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add ai-rate-card-mcp --url https://airatecard.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-rate-card-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "ai-rate-card-mcp": {
      "url": "https://airatecard.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "ai-rate-card-mcp": {
      "type": "streamableHttp",
      "url": "https://airatecard.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-rate-card-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "ai-rate-card-mcp": {
      "type": "http",
      "url": "https://airatecard.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http ai-rate-card-mcp https://airatecard.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://airatecard.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "ai-rate-card-mcp": {
      "serverUrl": "https://airatecard.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AI Rate Card MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,199

Do you run AI Rate Card MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing